Rethinking Randomized Smoothing from the Perspective of Scalability
Not on the map. Why?
Abstract (arXiv)
Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses obsolete, shifting the focus to certification-based defenses. Randomized smoothing has emerged as a promising technique among notable advancements. This study reviews the theoretical foundations and empirical effectiveness of randomized smoothing and its derivatives in verifying machine learning classifiers from a perspective of scalability. We provide an in-depth exploration of the fundamental concepts underlying randomized smoothing, highlighting its theoretical guarantees in certifying robustness against adversarial perturbations and discuss the challenges of existing methodologies.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 47 of its 61 references that are in the map. First posted on arXiv 19 Dec 2023.
Builds on
47 of 61 references.
References · 47
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Adversarial examples in the physical worldcited by 1,762
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Robustness May Be at Odds with Accuracycited by 873
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
- 2017Adversarial Patchcited by 514
35 more
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
- 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
- 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
- 2018Certified Adversarial Robustness with Additive Noisecited by 178
- 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
- 2020Randomized Smoothing of All Shapes and Sizescited by 146
- 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
- 2020(De)Randomized Smoothing for Certifiable Defense against Patch Attackscited by 97
- 2019Image Super-Resolution as a Defense Against Adversarial Attackscited by 64
- 2020Curse of Dimensionality on Randomized Smoothing for Certifiable Robustnesscited by 56
- 2021Boosting Randomized Smoothing with Variance Reduced Classifierscited by 47
- 2020Data-Dependent Randomized Smoothingcited by 37
- 2020Certifying Confidence via Randomized Smoothingcited by 36
- 2020Higher-Order Certification for Randomized Smoothingcited by 36
- 2019Certifiably Robust Interpretation in Deep Learningcited by 35
- 2020Random Smoothing Might be Unable to Certify ℓ_∞ Robustness for High-Dimensional Imagescited by 35
- 2021Intriguing Properties of Input-dependent Randomized Smoothingcited by 24
- 2021ANCER: Anisotropic Certification via Sample-wise Volume Maximizationcited by 23
- 2022Double Sampling Randomized Smoothingcited by 22
- 2022Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivitycited by 15
- 2022Robust and Accurate -- Compositional Architectures for Randomized Smoothingcited by 12
- 2023Incremental Randomized Smoothing Certificationcited by 12
- 2023Projected Randomized Smoothing for Certified Adversarial Robustnesscited by 11
- 2020Tight Second-Order Certificates for Randomized Smoothingcited by 10
- 2022Localized Randomized Smoothing for Collective Robustness Certificationcited by 10
- 2020Enhancing Certified Robustness via Smoothed Weighted Ensemblingcited by 7
- 2022Accelerating Certified Robustness Training via Knowledge Transfercited by 7
- 2023Understanding Noise-Augmented Training for Randomized Smoothingcited by 7
- 2020Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable Robustnesscited by 6
- 2022Certified Adversarial Robustness via Anisotropic Randomized Smoothingcited by 6
- 2020Hidden Cost of Randomized Smoothingcited by 5
- 2021Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracycited by 5
- 2022Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysiscited by 2
- 2022Smooth-Reduce: Leveraging Patches for Improved Certified Robustnesscited by 1
- 2022Riemannian data-dependent randomized smoothing for neural networks certificationcited by 1
Built on by
Citing papers per year: 2024: 2; 2025: 0; 2026: 1.
3 papers.